{"meta":{"query_hash":"a80b6dd78038","filters":{"venue":"International Journal of Data Warehousing and Mining"},"cohort_total":24,"direct_labels_cover":0,"predictions_cover":24,"exported":24,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/a80b6dd78038","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+of+Data+Warehousing+and+Mining"},"results":[{"id":"W1966404343","doi":"10.4018/jdwm.2012100103","title":"Efficient and Effective Aggregate Keyword Search on Relational Databases","year":2012,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Coquitlam College","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Aggregate (composite); Ranking (information retrieval); Keyword search; Relational database; Information retrieval; Keyword density; Database; Data mining","score_opus":0.08742456037480173,"score_gpt":0.3419586676621541,"score_spread":0.2545341072873524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966404343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6274195,0.001113869,0.36729133,0.001999619,0.0015163461,0.00008560344,0.00012812368,0.00002566957,0.00041993838],"genre_scores_gemma":[0.89185315,0.00011700764,0.10718716,0.00035145963,0.00039081593,5.686234e-7,0.00006032186,0.0000067595747,0.00003272498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891496,0.00005749801,0.00020433358,0.000184528,0.00048834766,0.00015035072],"domain_scores_gemma":[0.999098,0.0003188789,0.00016134536,0.00022456763,0.00010649694,0.00009072537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010491573,0.00008578477,0.00010070284,0.00022933027,0.000096584976,0.00019749245,0.00063556805,0.000013065542,0.000004254005],"category_scores_gemma":[0.00014654534,0.00007111464,0.000016138127,0.00008502306,0.000045078476,0.0014813532,0.0010254307,0.00013556641,0.0000036772535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058815924,0.00015219465,0.00814024,0.000009879204,0.00018346669,0.00008570134,0.0011681807,0.00067069416,0.00011099059,0.008064856,0.0026223457,0.97873265],"study_design_scores_gemma":[0.0047739656,0.000598199,0.09746931,0.0023685521,0.00013683233,0.0020980677,0.0010856237,0.6753384,0.0009964195,0.00026639507,0.21393102,0.0009372411],"about_ca_topic_score_codex":0.0000093987765,"about_ca_topic_score_gemma":5.853216e-7,"teacher_disagreement_score":0.9777954,"about_ca_system_score_codex":0.000026851041,"about_ca_system_score_gemma":0.000023451894,"threshold_uncertainty_score":0.2899971},"labels":[],"label_agreement":null},{"id":"W1974637590","doi":"10.4018/jdwm.2013040101","title":"Elasticity in Cloud Databases and Their Query Processing","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Provisioning; Cloud computing; Query optimization; Elasticity (physics); Range query (database); Database; Materialized view; Node (physics); Sargable; Key (lock); Online aggregation; Task (project management); Context (archaeology); Web query classification; View; Web search query; Distributed computing; Information retrieval; Computer network; Search engine; Operating system","score_opus":0.04858488775959593,"score_gpt":0.2912323829923285,"score_spread":0.24264749523273257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974637590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8230322,0.00078889675,0.17471395,0.0010034519,0.00032931461,0.00002772189,0.000004136319,0.0000152064495,0.00008510678],"genre_scores_gemma":[0.96269,0.00003922028,0.036812514,0.00018877514,0.00024925754,3.3204188e-7,0.000002848317,0.0000046817067,0.000012350603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915814,0.00003979963,0.0002913088,0.00019379587,0.00019669672,0.00012026575],"domain_scores_gemma":[0.9992884,0.00016592075,0.00020856576,0.00017108938,0.0001119335,0.00005411246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048514688,0.000085405496,0.00012635649,0.00018835257,0.000065500855,0.00034967976,0.00077035086,0.000015782032,0.0000019428587],"category_scores_gemma":[0.00011691893,0.00006423012,0.000013028741,0.00008497482,0.00003971725,0.00042204064,0.0011171966,0.00012881237,6.146776e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006901135,0.000048343874,0.0069045024,0.000016578668,0.00003605043,0.000068218185,0.0017511012,0.00083124853,0.00013889205,0.00012878262,0.00050327333,0.9895661],"study_design_scores_gemma":[0.0008175416,0.00006723539,0.01762545,0.0013049822,0.000011127083,0.00091132906,0.0019628468,0.9712345,0.00008614908,0.00046883003,0.005282767,0.00022725172],"about_ca_topic_score_codex":0.000104012644,"about_ca_topic_score_gemma":0.00001178499,"teacher_disagreement_score":0.9893389,"about_ca_system_score_codex":0.000020949956,"about_ca_system_score_gemma":0.00004038957,"threshold_uncertainty_score":0.337197},"labels":[],"label_agreement":null},{"id":"W1980161931","doi":"10.4018/jdwm.2008010103","title":"Dynamic View Selection for OLAP","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Materialized view; Online analytical processing; Computer science; Data warehouse; Aggregate (composite); Selection (genetic algorithm); Task (project management); Set (abstract data type); Information retrieval; Order (exchange); Data mining; Database; View; Machine learning","score_opus":0.06588151749652649,"score_gpt":0.3408887644985445,"score_spread":0.275007247002018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980161931","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041070815,0.00079551386,0.9569548,0.0003242765,0.0007355707,0.000031617394,0.000046985384,0.000016427304,0.00002398988],"genre_scores_gemma":[0.32651827,0.00030652192,0.67278683,0.000111897236,0.00019254973,8.47933e-7,0.00003374188,0.0000062752174,0.000043080738],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992867,0.000017101436,0.00026416953,0.0001436234,0.00020211919,0.00008625277],"domain_scores_gemma":[0.9992239,0.00009449306,0.00024514296,0.00014393545,0.00025342766,0.000039127528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029227437,0.00006244875,0.00011477822,0.00010687821,0.00011996253,0.000049236824,0.00048257736,0.000018104422,0.0000014079277],"category_scores_gemma":[0.00011233711,0.000053701813,0.000024528234,0.000060056227,0.000025308382,0.0018058155,0.00020766578,0.00006176051,5.233499e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009046468,0.00008226922,0.0023055514,0.000047016845,0.00024451315,0.0001407573,0.002300039,0.0005627027,0.002753984,0.0061574136,0.0044699055,0.9808454],"study_design_scores_gemma":[0.0019278622,0.00034149477,0.0015374727,0.0008796324,0.00003302604,0.01360604,0.00040869866,0.31310198,0.0005760414,0.00051529286,0.6666809,0.00039158677],"about_ca_topic_score_codex":0.0000105032705,"about_ca_topic_score_gemma":0.000011550184,"teacher_disagreement_score":0.9804538,"about_ca_system_score_codex":0.00002965196,"about_ca_system_score_gemma":0.00008534028,"threshold_uncertainty_score":0.21898964},"labels":[],"label_agreement":null},{"id":"W1998319238","doi":"10.4018/jdwm.2005100103","title":"Preference-Based Frequent Pattern Mining","year":2005,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Preference; Data mining; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Machine learning; Artificial intelligence; Data stream mining; Mathematics","score_opus":0.11674474253513491,"score_gpt":0.3223307267655304,"score_spread":0.20558598423039548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998319238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11948749,0.0003784098,0.8750373,0.0041913614,0.0004803753,0.00003377598,0.00009761994,0.00003907957,0.00025457452],"genre_scores_gemma":[0.5607445,0.00004122365,0.43826652,0.00046616173,0.00041189865,0.0000010114153,0.00004122799,0.000007006657,0.000020416368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870425,0.000029772484,0.00042048804,0.00026460714,0.00042845393,0.00015240458],"domain_scores_gemma":[0.99873376,0.00014980305,0.00035628284,0.00042797546,0.00023350347,0.000098671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005136557,0.00010989095,0.00014136179,0.00019057977,0.00009517387,0.00040980396,0.0020480843,0.00003453549,0.0000119505185],"category_scores_gemma":[0.00008929371,0.00009812839,0.000031168536,0.00009837413,0.00003747204,0.0015856939,0.00051680784,0.00013140845,0.0000044709795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037239668,0.000051626044,0.0009972539,0.0000027122335,0.000041640542,0.000024553825,0.00058461406,0.00019824039,0.0001454486,0.00009331469,0.0021956132,0.99566126],"study_design_scores_gemma":[0.0015424658,0.00014953493,0.0026134597,0.0006835218,0.000043806784,0.0006620946,0.00042037907,0.82935995,0.00077486393,0.00011776972,0.16325334,0.00037880024],"about_ca_topic_score_codex":0.000028198201,"about_ca_topic_score_gemma":0.000014913032,"teacher_disagreement_score":0.9952825,"about_ca_system_score_codex":0.00004607409,"about_ca_system_score_gemma":0.0001445982,"threshold_uncertainty_score":0.40015596},"labels":[],"label_agreement":null},{"id":"W1998415522","doi":"10.4018/ijdwm.2015010102","title":"Parallel Real-Time OLAP on Multi-Core Processors","year":2015,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Online analytical processing; Computer science; Data warehouse; Data cube; Benchmark (surveying); Database; Xeon Phi; Decision support system; Data mining; Parallel computing","score_opus":0.1509179829619319,"score_gpt":0.365363937577586,"score_spread":0.2144459546156541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998415522","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14081234,0.00043706395,0.85591763,0.00080785854,0.0012791645,0.00006202897,0.00011122816,0.000060940336,0.0005117557],"genre_scores_gemma":[0.16708623,0.00010975589,0.8318975,0.00018870975,0.00045824106,8.7234844e-7,0.000057737783,0.000013615267,0.00018733395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988639,0.00002808,0.00032961188,0.00020930474,0.00044817472,0.00012095354],"domain_scores_gemma":[0.9987981,0.00008447774,0.0003519743,0.00029639102,0.00034781985,0.00012127849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005667725,0.00010028178,0.00015782952,0.00013899773,0.000056889257,0.00011709385,0.000817732,0.00002756451,0.0000019084912],"category_scores_gemma":[0.00028209214,0.000079751364,0.00002104046,0.00007197226,0.000034481523,0.0018703669,0.0004541315,0.0001072715,0.000006773752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009111873,0.00084392214,0.007989847,0.000094387804,0.00081548095,0.003126578,0.025045361,0.011530998,0.0043421364,0.025102008,0.040905587,0.8792925],"study_design_scores_gemma":[0.0124805765,0.0016409495,0.0030596573,0.0048644133,0.00009077101,0.0074920664,0.005628699,0.53097624,0.001064913,0.0015866396,0.42945188,0.0016632276],"about_ca_topic_score_codex":0.000031534375,"about_ca_topic_score_gemma":0.0000061993705,"teacher_disagreement_score":0.8776293,"about_ca_system_score_codex":0.000039221093,"about_ca_system_score_gemma":0.00014507887,"threshold_uncertainty_score":0.32521662},"labels":[],"label_agreement":null},{"id":"W2004582297","doi":"10.4018/jdwm.2008100104","title":"Effectiveness of Fuzzy Classifier Rules in Capturing Correlations between Genes","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Classifier (UML); Computer science; Gene selection; Artificial intelligence; Fuzzy logic; Correlation; Fuzzy rule; Machine learning; Gene; Data mining; Pattern recognition (psychology); Fuzzy set; Mathematics; Genetics; Biology","score_opus":0.08223178487745361,"score_gpt":0.32237026324166423,"score_spread":0.24013847836421062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004582297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.775223,0.0004504337,0.22367492,0.00014063076,0.00022374642,0.000032659664,0.000090458234,0.000010020136,0.00015409212],"genre_scores_gemma":[0.8651454,0.00012519679,0.13454902,0.000007627864,0.00011538367,8.288611e-7,0.000044338125,0.000005268759,0.000006960558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99900234,0.000060180853,0.00039135292,0.00017947094,0.00027124243,0.00009541069],"domain_scores_gemma":[0.9987956,0.00044791918,0.00028661126,0.00025078276,0.00017320452,0.000045841785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006330763,0.000075736,0.00017927082,0.00025893547,0.00007182961,0.0000588835,0.0010089444,0.000034704062,9.0089316e-7],"category_scores_gemma":[0.00010595615,0.000070250004,0.000026216543,0.00013327865,0.00006411576,0.0010813787,0.00041465103,0.00012527224,8.6904925e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003787706,0.00019237073,0.18943909,0.00005178293,0.00027337304,0.00020594975,0.0039465236,0.0015244709,0.0026729256,0.0027636033,0.00032747549,0.79856455],"study_design_scores_gemma":[0.0037229334,0.00023313929,0.87488043,0.0032048258,0.000097220574,0.0023755434,0.0009155516,0.100298174,0.0033008454,0.0031135338,0.0071818684,0.0006759494],"about_ca_topic_score_codex":0.000074569514,"about_ca_topic_score_gemma":0.000004389824,"teacher_disagreement_score":0.79788864,"about_ca_system_score_codex":0.000030198786,"about_ca_system_score_gemma":0.00010633177,"threshold_uncertainty_score":0.2864712},"labels":[],"label_agreement":null},{"id":"W2008393584","doi":"10.4018/jdwm.2008100102","title":"Computing Join Aggregates Over Private Tables","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Join (topology); Computer science; Protocol (science); Private information retrieval; Matching (statistics); Inference; Computer security; Secret sharing; Theoretical computer science; Cryptography; Mathematics","score_opus":0.076248266712977,"score_gpt":0.3195461971826842,"score_spread":0.24329793046970716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008393584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62813985,0.00144982,0.36154833,0.007416133,0.0011233476,0.0000344819,0.000046765683,0.00011369789,0.00012757274],"genre_scores_gemma":[0.5178388,0.00045537128,0.4813552,0.00014686325,0.00017126875,1.04242886e-7,0.000017171466,0.000007813401,0.000007455484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985295,0.00004020674,0.0004443168,0.0002891398,0.00049825216,0.00019859914],"domain_scores_gemma":[0.9971656,0.00032814263,0.0005130001,0.0017500689,0.00018276126,0.00006041309],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00058884575,0.00012379306,0.00019004178,0.00027303485,0.00015937298,0.00025710027,0.017312277,0.000053751195,0.0000064261035],"category_scores_gemma":[0.0066934517,0.00011062647,0.000030901043,0.00016241253,0.00011524401,0.0024427422,0.04232091,0.0002254758,0.0000019598144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053971693,0.00017424984,0.046269566,0.000029894254,0.00052342843,0.0020850636,0.0016806299,0.0002643769,0.0024197209,0.0014719131,0.14078754,0.80423963],"study_design_scores_gemma":[0.0030588147,0.0002722034,0.016358051,0.0025077846,0.000052596897,0.016750678,0.00037157774,0.8287152,0.0046975096,0.020953361,0.105288975,0.00097322185],"about_ca_topic_score_codex":0.000055123997,"about_ca_topic_score_gemma":0.000005340197,"teacher_disagreement_score":0.82845086,"about_ca_system_score_codex":0.000048396538,"about_ca_system_score_gemma":0.000094475654,"threshold_uncertainty_score":0.9880045},"labels":[],"label_agreement":null},{"id":"W2037018161","doi":"10.4018/jdwm.2006010101","title":"Improved Data Partitioning for Building Large ROLAP Data Cubes in Parallel","year":2006,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Carleton University; Dalhousie University","funders":"","keywords":"Computer science; Parallel computing; Speedup; Scalability; Data cube; Data warehouse; Cube (algebra); Representation (politics); Multiprocessing; Materialized view; Online analytical processing; Data structure; External Data Representation; Parallel algorithm; Data mining; Database; Operating system","score_opus":0.07509153115286228,"score_gpt":0.3572573266976316,"score_spread":0.28216579554476934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037018161","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018700048,0.0013901301,0.9768124,0.00058527355,0.0006841354,0.00006814012,0.0017191223,0.00002021306,0.000020521165],"genre_scores_gemma":[0.29859528,0.00008457415,0.69912964,0.000086620435,0.00062333443,0.0000013475316,0.0014561529,0.000010923261,0.000012143562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984129,0.000038933962,0.00059381063,0.00045080928,0.00028044454,0.00022308959],"domain_scores_gemma":[0.99801314,0.0002457609,0.00042431706,0.0011055248,0.0001641934,0.00004707046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015097371,0.00011654705,0.00020610642,0.0001764813,0.00012613248,0.0002770921,0.0029371383,0.00003359261,0.0000017249923],"category_scores_gemma":[0.00037479738,0.00010654612,0.000017069253,0.00009482081,0.000028723745,0.0065320134,0.003066513,0.00012921648,3.530084e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007344723,0.0011316481,0.041357864,0.00032830003,0.00091011723,0.0011786727,0.0030255173,0.012037118,0.015257412,0.097193874,0.044713374,0.7821316],"study_design_scores_gemma":[0.0015479513,0.00004447195,0.0006775906,0.0005629503,0.00001896964,0.00032608668,0.00033191222,0.81682754,0.00008997669,0.0005783755,0.17878702,0.00020716651],"about_ca_topic_score_codex":0.00015231126,"about_ca_topic_score_gemma":0.00037450815,"teacher_disagreement_score":0.8047904,"about_ca_system_score_codex":0.000030399355,"about_ca_system_score_gemma":0.00011530903,"threshold_uncertainty_score":0.5457983},"labels":[],"label_agreement":null},{"id":"W2040900238","doi":"10.4018/jdwm.2013040105","title":"An Envisioned Approach for Modeling and Supporting User-Centric Query Activities on Data Warehouses","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Data warehouse; Online analytical processing; Metadata; Ontology; Information retrieval; Exploit; Knowledge extraction; Query optimization; Data mining; Data science; Database; World Wide Web","score_opus":0.09383134873528128,"score_gpt":0.3502786813204296,"score_spread":0.25644733258514835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040900238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1818278,0.0003081401,0.8170638,0.00019573777,0.00026886666,0.000086548935,0.00021047595,0.000026101805,0.000012538766],"genre_scores_gemma":[0.55820036,0.00010118627,0.44115314,0.00009170957,0.00025364576,0.0000018056268,0.00018045303,0.000011422837,0.0000062733384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852043,0.000050116938,0.00046488192,0.00041512016,0.00035660455,0.00019285687],"domain_scores_gemma":[0.9983898,0.000256926,0.00041148945,0.0006497327,0.00018466613,0.00010741641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007679967,0.00013811007,0.00021735294,0.00021489225,0.00018508304,0.00043889866,0.00129198,0.000036805628,0.0000018057458],"category_scores_gemma":[0.0002683805,0.00011343871,0.000019764904,0.00006357585,0.000037130903,0.007365358,0.0009320394,0.00012770458,2.609877e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114159535,0.00023276529,0.0015795969,0.00008772121,0.00022897054,0.000050505932,0.0028116514,0.011645739,0.001948377,0.0028314933,0.0012425605,0.97722644],"study_design_scores_gemma":[0.0005273292,0.0001219237,0.00006844238,0.00022475282,0.000014982383,0.0003001403,0.0022894382,0.99286556,0.00009399986,0.000087504086,0.00323642,0.00016948738],"about_ca_topic_score_codex":0.000074538344,"about_ca_topic_score_gemma":0.000004932836,"teacher_disagreement_score":0.9812198,"about_ca_system_score_codex":0.000023749102,"about_ca_system_score_gemma":0.00008392463,"threshold_uncertainty_score":0.53397065},"labels":[],"label_agreement":null},{"id":"W2044194343","doi":"10.4018/jdwm.2012100101","title":"Towards Comparative Mining of Web Document Objects with NFA","year":2012,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Web mining; Data Web; Web page; Web modeling; Information retrieval; Web standards; World Wide Web; Web intelligence; Static web page; Web navigation; Database","score_opus":0.07416393370134935,"score_gpt":0.3429523755542617,"score_spread":0.2687884418529124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044194343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9021004,0.0011288758,0.09463657,0.00044356278,0.0006182069,0.000028967112,0.000058411333,0.000019275874,0.0009657807],"genre_scores_gemma":[0.80079997,0.00005439534,0.19881465,0.000061879735,0.00022919477,2.933105e-7,0.000019241274,0.000005096284,0.000015309084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985283,0.00006508286,0.00043388584,0.00018481165,0.00060162245,0.00018630568],"domain_scores_gemma":[0.9984772,0.00017218976,0.0005957208,0.00032801606,0.0003092348,0.00011763825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008696044,0.00012386202,0.00028612488,0.00028727978,0.00006482331,0.00018240002,0.001293208,0.000028127899,0.000008112759],"category_scores_gemma":[0.00008982482,0.000093725495,0.00003924208,0.00018626289,0.00007195693,0.0024728742,0.00058330933,0.00011648715,0.0000010492475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003501978,0.0006714729,0.06613788,0.00007834087,0.0037855844,0.00032782785,0.07746766,0.0013355275,0.006732796,0.0025618651,0.006666624,0.83388424],"study_design_scores_gemma":[0.030053476,0.006674334,0.09047828,0.020913579,0.00348461,0.022334356,0.14577396,0.45972222,0.05415137,0.0010326764,0.15889253,0.006488613],"about_ca_topic_score_codex":0.000032131462,"about_ca_topic_score_gemma":0.000010929475,"teacher_disagreement_score":0.8273956,"about_ca_system_score_codex":0.000035962727,"about_ca_system_score_gemma":0.0001842414,"threshold_uncertainty_score":0.3822015},"labels":[],"label_agreement":null},{"id":"W2060490725","doi":"10.4018/jdwm.2008070101","title":"RCUBE","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Concordia University; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Online analytical processing; Computer science; Scalability; Search engine indexing; Materialized view; Scheme (mathematics); Multidimensional data; Volume (thermodynamics); Database index; Index (typography); Distributed computing; Data mining; Database; Information retrieval; Data warehouse; View; Database design; World Wide Web","score_opus":0.09224246699132363,"score_gpt":0.32406961971131504,"score_spread":0.2318271527199914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060490725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1040001,0.000861215,0.89325595,0.0005585951,0.0010215623,0.000013618036,0.000033371547,0.000019185994,0.00023638064],"genre_scores_gemma":[0.5695415,0.00027407877,0.4296029,0.00016315641,0.00035810968,1.42595e-7,0.000011613105,0.000004552013,0.000043948367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99923116,0.000019272853,0.000252304,0.00012892834,0.00028820976,0.00008010539],"domain_scores_gemma":[0.9992407,0.00007139526,0.0002148742,0.00024325216,0.0001783255,0.000051436746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025140276,0.000057836518,0.00010315512,0.00010339544,0.00008428431,0.000047461093,0.0007597198,0.000015375559,0.0000029922035],"category_scores_gemma":[0.00011078138,0.00004774539,0.00001798574,0.000053919368,0.000040897612,0.002180802,0.0005032255,0.00007516554,0.000001575019],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052476564,0.00010461652,0.009105362,0.000017754017,0.00028164452,0.003141355,0.006482043,0.000292299,0.0021314896,0.016637802,0.015019733,0.9467334],"study_design_scores_gemma":[0.0015457129,0.00014587426,0.0044193817,0.0006113305,0.00001694265,0.026065579,0.0008054179,0.020872967,0.00074417755,0.0003417441,0.9440521,0.00037877992],"about_ca_topic_score_codex":0.000013787269,"about_ca_topic_score_gemma":0.0000025251663,"teacher_disagreement_score":0.9463546,"about_ca_system_score_codex":0.000014552367,"about_ca_system_score_gemma":0.00007635431,"threshold_uncertainty_score":0.19470005},"labels":[],"label_agreement":null},{"id":"W2067774887","doi":"10.4018/jdwm.2010070103","title":"Classification of Peer-to-Peer Traffic Using A Two-Stage Window-Based Classifier With Fast Decision Tree and IP Layer Attributes","year":2010,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Traffic classification; Classifier (UML); Router; Decision tree; Data mining; The Internet; Peer-to-peer; Internet traffic; Artificial intelligence; Machine learning; Computer network; Network packet","score_opus":0.07563901748133242,"score_gpt":0.3311798451447369,"score_spread":0.25554082766340447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067774887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70666474,0.000040688097,0.2917537,0.00095155253,0.00048927113,0.000041546726,0.000026292575,0.000011650174,0.000020524927],"genre_scores_gemma":[0.85171974,0.0000063550197,0.14792255,0.00009624239,0.00021672063,4.3249713e-7,0.000012203187,0.0000089275345,0.000016821989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982791,0.00004656959,0.0004305005,0.0002784677,0.0008265884,0.00013877926],"domain_scores_gemma":[0.9979422,0.00026048842,0.00044780766,0.0003005133,0.0009337341,0.00011526116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010504387,0.00012501956,0.00019183499,0.00036120557,0.0001258691,0.00030686968,0.0007191653,0.000065403205,0.000008064064],"category_scores_gemma":[0.00027523164,0.000101782076,0.00003072512,0.00021926298,0.000076285374,0.0011938285,0.00023291027,0.00028438008,4.934106e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041731945,0.00013356748,0.004021558,0.000013395633,0.000096090276,0.000054240125,0.001408723,0.009733878,0.051299416,0.00037711667,0.0005001101,0.9319446],"study_design_scores_gemma":[0.0021804923,0.0003594621,0.013191331,0.00059956365,0.000048885853,0.0006044807,0.0004022567,0.96841353,0.00378803,0.0000715326,0.010087023,0.00025338584],"about_ca_topic_score_codex":0.000020278067,"about_ca_topic_score_gemma":0.0001553095,"teacher_disagreement_score":0.9586797,"about_ca_system_score_codex":0.000029351508,"about_ca_system_score_gemma":0.00013776749,"threshold_uncertainty_score":0.41505527},"labels":[],"label_agreement":null},{"id":"W2072801150","doi":"10.4018/jdwm.2013070101","title":"Efficient Top-k Keyword Search Over Multidimensional Databases","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Keyword search; Online analytical processing; Perspective (graphical); Database; Search algorithm; Search engine; Search engine indexing; Information retrieval; Data mining; Algorithm; Artificial intelligence; Data warehouse","score_opus":0.061530596177754776,"score_gpt":0.33968236031463683,"score_spread":0.27815176413688203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072801150","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40830132,0.00049123616,0.58985156,0.00035311765,0.0007832623,0.000042169297,0.00009636523,0.000017079563,0.00006388121],"genre_scores_gemma":[0.4506498,0.00004688804,0.54870737,0.00018858544,0.00031677898,8.0424445e-7,0.000047759266,0.000007898272,0.00003416017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985609,0.00004824626,0.0003803662,0.00025171926,0.00059261103,0.00016615403],"domain_scores_gemma":[0.99867755,0.0002252919,0.00021919505,0.00039754,0.00037292493,0.00010748945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004741302,0.000105525054,0.00015300202,0.00018086823,0.00010215117,0.00011600666,0.00067509065,0.000019206753,0.00003620505],"category_scores_gemma":[0.0001595473,0.000083645944,0.00002841452,0.000088343295,0.00005600739,0.0016143952,0.0012751946,0.00013876136,0.000008637793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011229487,0.00040887395,0.011233059,0.00005858739,0.00048584616,0.000810519,0.0041317833,0.0109505635,0.01611048,0.043457624,0.015744844,0.8964955],"study_design_scores_gemma":[0.0025955385,0.00018818257,0.013001681,0.001534491,0.00003187327,0.0030805424,0.0021199607,0.7460833,0.0020016022,0.00007972668,0.22861502,0.00066808495],"about_ca_topic_score_codex":0.00017283589,"about_ca_topic_score_gemma":0.000004708655,"teacher_disagreement_score":0.8958274,"about_ca_system_score_codex":0.000030885498,"about_ca_system_score_gemma":0.00010231535,"threshold_uncertainty_score":0.34109825},"labels":[],"label_agreement":null},{"id":"W2091140227","doi":"10.4018/jdwm.2010070102","title":"Exploring Disease Association from the NHANES Data","year":2010,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Automatic summarization; Disease; Association rule learning; Data mining; Association (psychology); Data science; Artificial intelligence; Medicine; Pathology; Psychology","score_opus":0.21387985509449203,"score_gpt":0.33851251238262725,"score_spread":0.12463265728813522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091140227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7007981,0.00056368374,0.26996112,0.021403085,0.005164893,0.000068043126,0.0018809792,0.00006305564,0.00009706076],"genre_scores_gemma":[0.6934393,0.0004055799,0.30266348,0.0004706776,0.002378265,0.0000022120366,0.00059262966,0.000012408265,0.000035454876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887425,0.00002985214,0.00027350915,0.0002535826,0.00046491218,0.000103873994],"domain_scores_gemma":[0.9978569,0.00055322563,0.00035537255,0.0009606755,0.00018985308,0.000083985964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009613545,0.00007343852,0.00008797278,0.000054577336,0.00014902362,0.00065696414,0.0042397403,0.00002016461,0.000005606701],"category_scores_gemma":[0.00082712213,0.000054091553,0.000016906222,0.00008437615,0.000025598087,0.0037567636,0.0018150846,0.00023680415,0.0000034167506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009065144,0.00004946234,0.0069354377,0.0000014783457,0.00013144611,0.00003722268,0.0010641896,0.0000129640675,0.00073705084,0.0005415835,0.01013059,0.9803495],"study_design_scores_gemma":[0.001082025,0.00003582091,0.061326403,0.00039107024,0.00016491108,0.00019667041,0.001050139,0.29268166,0.0002360948,0.0013197936,0.64108914,0.00042625796],"about_ca_topic_score_codex":0.00011175907,"about_ca_topic_score_gemma":0.000042771462,"teacher_disagreement_score":0.97992325,"about_ca_system_score_codex":0.000018373505,"about_ca_system_score_gemma":0.0001046622,"threshold_uncertainty_score":0.7878563},"labels":[],"label_agreement":null},{"id":"W2100729317","doi":"10.4018/jdwm.2006070102","title":"A TOPSIS Data Mining Demonstration and Application to Credit Scoring","year":2006,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TOPSIS; Ideal solution; Computer science; Data mining; Similarity (geometry); Classifier (UML); Machine learning; Artificial intelligence; Operations research; Mathematics","score_opus":0.05886790145175001,"score_gpt":0.31690642003769104,"score_spread":0.258038518585941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100729317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20348482,0.0004211233,0.79352266,0.0017335453,0.00042577094,0.000044536187,0.000055283876,0.000020845686,0.00029142943],"genre_scores_gemma":[0.6664827,0.00003835949,0.33281457,0.0001234735,0.00047701053,4.5654596e-7,0.000054685825,0.0000042236807,0.000004552845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890596,0.000022630275,0.00034152798,0.0003008742,0.0003160063,0.000113016555],"domain_scores_gemma":[0.9990449,0.00010688174,0.0002403798,0.00041113413,0.00013273643,0.00006399212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006148245,0.00008350239,0.00011621661,0.00016786231,0.00010509267,0.00046883884,0.0013586016,0.000029679546,9.705301e-7],"category_scores_gemma":[0.00010227725,0.00007594861,0.000010701003,0.00010924598,0.000024244713,0.0018605379,0.001028868,0.00007499694,5.581306e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015643955,0.00003086207,0.0062029664,0.0000057564266,0.000034761102,0.000043606164,0.00048028326,0.00042963028,0.0009522177,0.0005585174,0.0020909104,0.9891548],"study_design_scores_gemma":[0.0014728764,0.00026152533,0.03389393,0.00072425045,0.00008614143,0.0024604592,0.0010276543,0.91528785,0.0003175977,0.001601127,0.042286295,0.000580262],"about_ca_topic_score_codex":0.0000805041,"about_ca_topic_score_gemma":0.00003656387,"teacher_disagreement_score":0.98857456,"about_ca_system_score_codex":0.000022662274,"about_ca_system_score_gemma":0.000053719043,"threshold_uncertainty_score":0.4521024},"labels":[],"label_agreement":null},{"id":"W2128322880","doi":"10.4018/jdwm.2005040101","title":"The Use of Smart Tokens in Cleaning Integrated Warehouse Data","year":2005,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data warehouse; Security token; Database; Alphanumeric; Matching (statistics); Data mining; Unique identifier; Identifier; Computer security","score_opus":0.5821457750325668,"score_gpt":0.47436071499941795,"score_spread":0.10778506003314886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128322880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92222226,0.001280303,0.05856626,0.013493236,0.002221673,0.0001600704,0.0017391635,0.000025577168,0.00029147408],"genre_scores_gemma":[0.9577079,0.000624631,0.040554605,0.00052630255,0.00025410892,2.8920726e-7,0.00013728805,0.000012135222,0.00018273189],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686223,0.00023211338,0.0012441047,0.0002994127,0.001202144,0.00015997453],"domain_scores_gemma":[0.9953704,0.0022580156,0.0008217167,0.0010379534,0.00044961183,0.000062341845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069025056,0.00010224451,0.00023141582,0.00036150982,0.0001041627,0.00072538835,0.0038841926,0.00003392077,0.000024486024],"category_scores_gemma":[0.007062009,0.0000656079,0.00003136472,0.00025289075,0.00012865584,0.003771463,0.0023577914,0.00021561277,0.000004682942],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018133433,0.0000729918,0.004116633,0.0000023004206,0.00009823968,0.000047148038,0.0011775099,0.0013580807,0.000052210835,0.00023706906,0.042115923,0.95054054],"study_design_scores_gemma":[0.0006335841,0.000053594722,0.0022566149,0.00027160277,0.000025671114,0.00009836535,0.0046516424,0.049230497,0.000048526148,0.00018970392,0.9424344,0.00010584741],"about_ca_topic_score_codex":0.00020505837,"about_ca_topic_score_gemma":0.0015587712,"teacher_disagreement_score":0.9504347,"about_ca_system_score_codex":0.00004203997,"about_ca_system_score_gemma":0.00011139021,"threshold_uncertainty_score":0.84543943},"labels":[],"label_agreement":null},{"id":"W2171228059","doi":"10.4018/jdwm.2010090801","title":"Investigating the Properties of a Social Bookmarking and Tagging Network","year":2010,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Bookmarking; Similarity (geometry); Social network (sociolinguistics); Set (abstract data type); World Wide Web; Friendship; Meaning (existential); Popularity; Information retrieval; Social media; Artificial intelligence","score_opus":0.0489664359810364,"score_gpt":0.30693320963499304,"score_spread":0.25796677365395665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171228059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99525726,0.00021809089,0.0033897515,0.00063274597,0.00016533978,0.000025866793,0.0000075079247,0.000006749371,0.0002966865],"genre_scores_gemma":[0.9846792,0.0000061524006,0.013928361,0.000062331754,0.0013032649,4.763904e-7,0.000006194861,0.000007722163,0.0000062679446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928075,0.000034602883,0.00031245052,0.00009217806,0.00018868277,0.000091336944],"domain_scores_gemma":[0.9991904,0.00009291381,0.00044964085,0.000098498684,0.00014295314,0.00002561458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006732627,0.00007028472,0.00014288408,0.000055546123,0.00016896633,0.00012433146,0.0003674817,0.00001596189,0.000010217264],"category_scores_gemma":[0.000040021972,0.000049760976,0.00003203447,0.00005362451,0.0001311105,0.00029030748,0.00035428104,0.00022343904,4.387209e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037972557,0.000050573784,0.15104981,0.000022518832,0.0009351991,0.000006001223,0.008231088,0.00024778186,0.03937578,0.007064834,0.0032090815,0.78976935],"study_design_scores_gemma":[0.007435605,0.00047571436,0.08053376,0.011799026,0.0027956576,0.0013436225,0.045281075,0.4999305,0.025949875,0.04964803,0.27162057,0.003186576],"about_ca_topic_score_codex":0.000058066635,"about_ca_topic_score_gemma":0.000013530138,"teacher_disagreement_score":0.78658277,"about_ca_system_score_codex":0.0000042996508,"about_ca_system_score_gemma":0.000041723117,"threshold_uncertainty_score":0.20291938},"labels":[],"label_agreement":null},{"id":"W2563061479","doi":"10.4018/ijdwm.2017010103","title":"Multidimensional Business Benchmarking Analysis on Data Warehouses","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Benchmarking; Computer science; Data warehouse; Benchmark (surveying); Business intelligence; Aggregate (composite); Data science; Online analytical processing; Scalability; Context (archaeology); Analytics; Data mining; Set (abstract data type); Data cube; Business analytics; Database; Business model; Business analysis","score_opus":0.07877539273770963,"score_gpt":0.3369665008377868,"score_spread":0.25819110810007717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563061479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057593804,0.00032993956,0.93901217,0.001409686,0.0010963975,0.000025126932,0.00047023283,0.000028251512,0.00003436452],"genre_scores_gemma":[0.5717831,0.0002653685,0.4269221,0.00019872525,0.0006389442,3.6640193e-7,0.00015272982,0.000011223117,0.000027389591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982057,0.000060136157,0.0004857917,0.0004469937,0.0006390293,0.000162326],"domain_scores_gemma":[0.9974435,0.00049794716,0.0004962443,0.0010282756,0.0004460959,0.00008794117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080511556,0.0001384901,0.0002576165,0.00044556792,0.00011541009,0.00011376753,0.0018665144,0.000032744065,0.000013201407],"category_scores_gemma":[0.000484533,0.00008887575,0.000037340556,0.00030972072,0.000061728715,0.0036080256,0.0020061315,0.00008747837,0.0000028376198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008883423,0.000097368255,0.007467335,0.000009770807,0.0011309064,0.00040699248,0.00035530532,0.0007431935,0.0015012475,0.003386133,0.002095668,0.9827172],"study_design_scores_gemma":[0.006173799,0.0004938063,0.0603618,0.0062481766,0.0008965997,0.0028966086,0.00081958785,0.18019865,0.0012018227,0.000324592,0.73854685,0.0018377252],"about_ca_topic_score_codex":0.00004042204,"about_ca_topic_score_gemma":0.000032237123,"teacher_disagreement_score":0.98087955,"about_ca_system_score_codex":0.000041294177,"about_ca_system_score_gemma":0.00012455853,"threshold_uncertainty_score":0.3624248},"labels":[],"label_agreement":null},{"id":"W2892991540","doi":"10.4018/ijdwm.2018100103","title":"An Encryption Methodology for Enabling the Use of Data Warehouses on the Cloud","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Encryption; Computer science; Client-side encryption; Filesystem-level encryption; Cloud computing; Homomorphic encryption; On-the-fly encryption; 40-bit encryption; 56-bit encryption; Database; Computer security; Operating system","score_opus":0.5255598604403172,"score_gpt":0.4357902813132018,"score_spread":0.08976957912711542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892991540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13553202,0.00016469216,0.86105746,0.001787726,0.0010061254,0.000062926694,0.0003711609,0.000012799517,0.000005059815],"genre_scores_gemma":[0.56903493,0.00014324038,0.42910454,0.00065379316,0.0009719296,6.48842e-7,0.00008307656,0.000007190042,6.601307e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986313,0.0002596311,0.0003808334,0.00026769206,0.00033408304,0.0001264809],"domain_scores_gemma":[0.9954427,0.0025384205,0.00047334618,0.0010981573,0.00040672216,0.000040660016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002925618,0.00009082051,0.00014172799,0.00015044626,0.00021989402,0.00033989057,0.0038993682,0.000037641796,0.000004461756],"category_scores_gemma":[0.0011806055,0.000052893487,0.000035474503,0.00012947683,0.00018395926,0.0026809843,0.00094169204,0.00014463268,3.4108277e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048050244,0.00021901193,0.00091841066,0.000016097521,0.00043028453,0.000018238912,0.0073666763,0.00019158411,0.004037202,0.051764216,0.009375149,0.92518264],"study_design_scores_gemma":[0.0024904953,0.0024405879,0.0028376286,0.0011077311,0.00029080096,0.0011919705,0.0043047466,0.359586,0.0072441646,0.018918406,0.5989185,0.0006689761],"about_ca_topic_score_codex":0.00005611709,"about_ca_topic_score_gemma":0.00004587971,"teacher_disagreement_score":0.92451364,"about_ca_system_score_codex":0.000010082972,"about_ca_system_score_gemma":0.000080620885,"threshold_uncertainty_score":0.72460616},"labels":[],"label_agreement":null},{"id":"W2989849422","doi":"10.4018/ijdwm.2020010101","title":"Mining Integrated Sequential Patterns From Multiple Databases","year":2019,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Royal Bank of Canada; University of Windsor","funders":"","keywords":"Computer science; Tuple; Sequence (biology); Database transaction; Sequence database; Data mining; GSP Algorithm; Table (database); Database; Position (finance); Association rule learning; Apriori algorithm; Mathematics","score_opus":0.0751542230104232,"score_gpt":0.3248460621996281,"score_spread":0.2496918391892049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989849422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59319896,0.00015986663,0.4044153,0.00033313243,0.0009870235,0.00003283124,0.0007950754,0.000028255072,0.00004953701],"genre_scores_gemma":[0.640685,0.00006748219,0.35809425,0.00015906218,0.000314157,6.8587525e-7,0.00063833536,0.000010430333,0.00003057209],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985904,0.000042382446,0.0004393947,0.00035863245,0.00041475837,0.00015442623],"domain_scores_gemma":[0.9983802,0.00033546172,0.00038898652,0.0005741559,0.00023149562,0.00008972843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003973938,0.00012994323,0.00019118663,0.00017698777,0.000071706076,0.00043191403,0.002013834,0.000031564658,0.00003598],"category_scores_gemma":[0.00016013654,0.000115138246,0.000034824392,0.00009652906,0.000028300143,0.0023140186,0.0011363858,0.00016371551,0.000009441925],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037889204,0.000120273464,0.044870757,0.000008865843,0.00031554658,0.00015514823,0.0019090573,0.00012243501,0.0041861576,0.00030685612,0.0035966395,0.9443704],"study_design_scores_gemma":[0.0032679564,0.00017795294,0.010457582,0.0016711995,0.00009626555,0.00089228025,0.0032926323,0.80135024,0.002381547,0.00014113406,0.17557424,0.0006969728],"about_ca_topic_score_codex":0.00045811734,"about_ca_topic_score_gemma":0.000042804535,"teacher_disagreement_score":0.9436734,"about_ca_system_score_codex":0.000034859582,"about_ca_system_score_gemma":0.00012187111,"threshold_uncertainty_score":0.46952015},"labels":[],"label_agreement":null},{"id":"W3032597430","doi":"10.4018/ijdwm.2020070106","title":"Conceptual Model and Design of Semantic Trajectory Data Warehouse","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data warehouse; Trajectory; Data mining; Geospatial analysis; Context (archaeology); Ontology; Inference; Object (grammar); Semantic data model; Information retrieval; Data modeling; Data science; Database; Artificial intelligence","score_opus":0.22540462770170883,"score_gpt":0.32539442731228885,"score_spread":0.09998979961058002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032597430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020168133,0.000683671,0.97746456,0.0012167981,0.00021658595,0.000040189654,0.00016730314,0.000018995046,0.00002376861],"genre_scores_gemma":[0.64635235,0.00031970176,0.35276544,0.00033441925,0.00016168132,1.2426197e-7,0.00005143497,0.000007860447,0.0000070011306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988208,0.000044588123,0.00036077143,0.00028511492,0.0003858115,0.0001029576],"domain_scores_gemma":[0.9989505,0.00013837518,0.0003056954,0.00040391993,0.00011437532,0.000087142354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000569351,0.00009464021,0.00018045232,0.00010680837,0.000042238695,0.00019887874,0.002674123,0.000022282342,0.0000025449026],"category_scores_gemma":[0.00018681667,0.000084805535,0.000013948088,0.00007775175,0.00008786968,0.0029467742,0.0022419237,0.00010800197,4.879834e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022897215,0.00021108071,0.0014985688,0.00009684428,0.0009906418,0.00065160025,0.016339704,0.031129457,0.003624629,0.0029143996,0.02925013,0.91306394],"study_design_scores_gemma":[0.00061461114,0.00008912764,0.00008842414,0.000119872864,0.000037298625,0.000081169936,0.00047366595,0.99668765,0.00006832804,0.00008395451,0.0015533143,0.00010257036],"about_ca_topic_score_codex":0.0000072556954,"about_ca_topic_score_gemma":0.0000011928955,"teacher_disagreement_score":0.96555823,"about_ca_system_score_codex":0.0000074523637,"about_ca_system_score_gemma":0.00008837933,"threshold_uncertainty_score":0.49692303},"labels":[],"label_agreement":null},{"id":"W3127102899","doi":"10.4018/ijdwm.2021010103","title":"Scalable Biclustering Algorithm Considers the Presence or Absence of Properties","year":2021,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Biclustering; Computer science; Scalability; Context (archaeology); Set (abstract data type); Exploit; Data mining; Matrix (chemical analysis); Binary number; Homogeneous; Column (typography); Algorithm; Theoretical computer science; Cluster analysis; Artificial intelligence; Database; Mathematics","score_opus":0.0837448108144359,"score_gpt":0.3264471138996301,"score_spread":0.2427023030851942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127102899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95045894,0.005815497,0.04111875,0.0015721723,0.00079551275,0.00004543628,0.00004163649,0.000003414945,0.00014865927],"genre_scores_gemma":[0.98400474,0.00078557094,0.014613012,0.00014601485,0.00018682206,6.3959135e-7,0.00001589466,0.0000055451046,0.00024173704],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940455,0.00003743992,0.00020665658,0.000117042655,0.00017670942,0.000057584522],"domain_scores_gemma":[0.99926454,0.000026629445,0.00018860023,0.00018108224,0.00031451005,0.000024641182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002177208,0.00004757305,0.00006905847,0.000029498668,0.00004493955,0.000043627475,0.00028832763,0.000025431753,0.00000928747],"category_scores_gemma":[0.00027040913,0.000030112862,0.000018305276,0.00004156228,0.000073703835,0.000025347006,0.00026750172,0.00004955044,1.355598e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011502816,0.000031517484,0.000861557,0.00001559923,0.00011306514,0.000025611398,0.00047561154,0.00027148036,0.7949956,0.000006780687,0.0033572416,0.19973089],"study_design_scores_gemma":[0.0014011284,0.00020874868,0.0016237961,0.0012383849,0.00005377409,0.0021564302,0.011700969,0.012759577,0.8237432,0.000040342846,0.14482838,0.00024521496],"about_ca_topic_score_codex":0.000008071999,"about_ca_topic_score_gemma":0.000008344597,"teacher_disagreement_score":0.19948567,"about_ca_system_score_codex":0.00000551879,"about_ca_system_score_gemma":0.0001945965,"threshold_uncertainty_score":0.122796685},"labels":[],"label_agreement":null},{"id":"W4294982430","doi":"10.4018/ijdwm.309957","title":"A Stock Trading Expert System Established by the CNN-GA-Based Collaborative System","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Natural Science Foundation of Shandong Province","keywords":"Computer science; Futures contract; Stock (firearms); Convolutional neural network; Stock exchange; Stock market; Artificial intelligence; Data mining; Finance; Business","score_opus":0.17586435733785302,"score_gpt":0.4223358107247798,"score_spread":0.2464714533869268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294982430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6657228,0.0050275894,0.30780864,0.0044045616,0.010930034,0.00046104586,0.0015767424,0.000120284814,0.0039483327],"genre_scores_gemma":[0.96569586,0.0000033159045,0.033568274,0.00020670239,0.00037397654,0.000008511211,0.000023738547,0.000021854728,0.00009777551],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942949,0.0013584648,0.0010757578,0.0004023763,0.0026597085,0.00020880366],"domain_scores_gemma":[0.9921541,0.004896865,0.0014428433,0.00052398304,0.00087320775,0.000109007335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012788547,0.00016653704,0.0003702797,0.0004569479,0.00069955614,0.00097316573,0.0029265704,0.000035044013,0.000056432724],"category_scores_gemma":[0.003989243,0.00011277503,0.00007726033,0.0006669258,0.000091295275,0.0008943987,0.00078569347,0.00034741845,8.913957e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013066644,0.00014956601,0.004319485,0.00003150387,0.00054467877,0.0006422574,0.014006686,0.0049269875,0.0024038234,0.0003014606,0.2155238,0.7558431],"study_design_scores_gemma":[0.0029753898,0.00045238383,0.00046616758,0.0009686678,0.00011205349,0.004714587,0.1801815,0.60818803,0.00042968965,0.000091164584,0.2009457,0.0004746393],"about_ca_topic_score_codex":0.000046209952,"about_ca_topic_score_gemma":0.0000041910907,"teacher_disagreement_score":0.7553685,"about_ca_system_score_codex":0.0004014318,"about_ca_system_score_gemma":0.00040560088,"threshold_uncertainty_score":0.93842596},"labels":[],"label_agreement":null},{"id":"W4319991217","doi":"10.4018/ijdwm.316150","title":"Top-K Pseudo Labeling for Semi-Supervised Image Classification","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Key (lock); Semi-supervised learning; Supervised learning; Set (abstract data type); Pattern recognition (psychology); Labeled data; Training set; Convergence (economics); Data mining","score_opus":0.07460392936922271,"score_gpt":0.34534800968852597,"score_spread":0.27074408031930325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319991217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082143135,0.0004366539,0.9084452,0.007275275,0.0012269749,0.00007846697,0.0001681248,0.000049996455,0.00017618375],"genre_scores_gemma":[0.6478644,0.00007686983,0.35104597,0.00034927786,0.00032283607,0.00000489933,0.00027188365,0.000011622301,0.000052256215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987031,0.00008991107,0.00038621988,0.00026560738,0.0004336693,0.00012147605],"domain_scores_gemma":[0.9986292,0.00024378927,0.0004259292,0.0003701909,0.0002755553,0.00005531214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013189707,0.000083669154,0.00012185061,0.00022170784,0.00028210087,0.00032464362,0.0016863896,0.000020988897,0.000012512809],"category_scores_gemma":[0.00035184014,0.00008301834,0.00003532903,0.00012503884,0.00002152141,0.0012880481,0.0007167245,0.00020100176,8.9546575e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093800765,0.00011664612,0.0023418276,0.000019242521,0.000109063294,0.00003031364,0.0019837562,0.0006510102,0.020373752,0.0037293686,0.006655739,0.9638955],"study_design_scores_gemma":[0.00123173,0.00015891415,0.0013067442,0.00007083478,0.00003087813,0.00056729326,0.0013427894,0.8734962,0.00018024475,0.00048982084,0.12093358,0.00019101682],"about_ca_topic_score_codex":0.000013089778,"about_ca_topic_score_gemma":0.0000013598731,"teacher_disagreement_score":0.96370447,"about_ca_system_score_codex":0.000064350854,"about_ca_system_score_gemma":0.00012448666,"threshold_uncertainty_score":0.33853897},"labels":[],"label_agreement":null}]}